From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

2025-03-15

AI Summary

In real-world surveillance, visible-infrared person re-identification (VI-ReID) faces critical privacy and data ownership challenges due to cross-device data distribution. Method: This paper introduces L2RW—the first privacy-preserving federated learning benchmark for VI-ReID tailored to realistic scenarios. L2RW supports either full data isolation or hierarchical selective sharing, enabling cross-modal feature alignment and decentralized training under multi-level privacy sensitivity modeling. It integrates customized federated protocols, cross-domain feature disentanglement, and privacy-tiered collaborative mechanisms. Results: Under strict data isolation, our approach achieves cross-domain generalization performance on unseen identities comparable to state-of-the-art centralized methods trained on full data (mAP/Rank-1: 68.3%/89.1%), significantly bridging the lab-to-real-world gap. This demonstrates the practical feasibility of privacy-compliant VI-ReID deployment in real surveillance systems.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Aiming to match pedestrian images captured under varying lighting conditions, visible-infrared person re-identification (VI-ReID) has drawn intensive research attention and achieved promising results. However, in real-world surveillance contexts, data is distributed across multiple devices/entities, raising privacy and ownership concerns that make existing centralized training impractical for VI-ReID. To tackle these challenges, we propose L2RW, a benchmark that brings VI-ReID closer to real-world applications. The rationale of L2RW is that integrating decentralized training into VI-ReID can address privacy concerns in scenarios with limited data-sharing regulation. Specifically, we design protocols and corresponding algorithms for different privacy sensitivity levels. In our new benchmark, we ensure the model training is done in the conditions that: 1) data from each camera remains completely isolated, or 2) different data entities (e.g., data controllers of a certain region) can selectively share the data. In this way, we simulate scenarios with strict privacy constraints which is closer to real-world conditions. Intensive experiments with various server-side federated algorithms are conducted, showing the feasibility of decentralized VI-ReID training. Notably, when evaluated in unseen domains (i.e., new data entities), our L2RW, trained with isolated data (privacy-preserved), achieves performance comparable to SOTAs trained with shared data (privacy-unrestricted). We hope this work offers a novel research entry for deploying VI-ReID that fits real-world scenarios and can benefit the community.

Problem

• Address privacy concerns in visible-infrared person re-identification.
• Propose decentralized training for real-world surveillance applications.
• Simulate strict privacy constraints with isolated data sharing.

Innovation

• Decentralized training for privacy-preserved VI-ReID.
• Protocols for varying privacy sensitivity levels.
• Federated algorithms for isolated data training.